~/can-i-run/gpt-oss-120b
OpenAI

Can I run gpt-oss 120B?

Short answer: yes, on a M3 Ultra 512 (512GB) at FP16/BF16. Long answer below.

gpt-oss:120bLM StudiovLLMMLXoMLX

The math, in one paragraph.

$ ./vrambudget --explain gpt-oss-120b

gpt-oss 120B has 117B parameters (MoE: 5.1B active per forward pass, but all 117B must fit in memory). At FP16 that's 234 GB of raw weights. Quantization shrinks that, but you also need budget for the KV cache (definition), framework overhead, and safety headroom. The rule of thumb: real usable budget on a card is roughly its nameplate VRAM minus 25%. That's how the table below was computed.

What hardware actually fits.

$ grep "fits" gpus.json
FP16/BF16
234GB
1 GPU fits
M3 Ultra 512512GB
Q8_0
124GB
5 GPUs fit
2× H100 NVL188GBM2 Ultra 192192GBB200192GBMI300X192GB+ 1 more
Q5_K_M
80GB
10 GPUs fit
M4 Max 128128GBM5 Max 128128GBDGX Spark128GBGaudi 3128GB+ 6 more
Q4_K_M
66GB
12 GPUs fit
M3 Max 9696GBRTX Pro 600096GBM4 Max 128128GBM5 Max 128128GB+ 8 more
Q3_K_M
50GB
17 GPUs fit
M2 Max 6464GBM3 Max 6464GBM4 Pro 6464GBM5 Pro 6464GB+ 13 more

Pick your path.

$ ls strategies/
Tightest budget

Smallest GPU that fits gpt-oss 120B at any quant: M3 Ultra 512 at FP16/BF16.

Reference quality (FP16)

Lossless inference needs 234 GB. Pick from 1 cards.

Best quality on a 24GB card

None of the showcase quants fit on a 24GB card. Step up.

Tune the math yourself

Open the calculator pre-tuned for gpt-oss 120B: ↗ /calc?model=gpt-oss-120b

See the full model page.

$ ./open
$ opengpt-oss 120B117BOpenAI · ctx 128K$ rankBest GPU for gpt-oss 120Bsee the ranking →ranked by fit quality

Discussion.

$ gh discussion list

// sign in with github to leave a comment. threads live in the repo's discussions tab.